Model comparison
o3-mini vs Qwen3.5 397B-A17B
Qwen3.5 397B-A17B is the stronger model overall, scoring 46.0 to 36.7 on the Noometry Index.
Last verified . 25 shared benchmarks.
Alibaba (Qwen)Summary
- They share 25 benchmarks with published results for both. o3-mini scores higher in 1 category and Qwen3.5 397B-A17B in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Qwen3.5 397B-A17B leads 34.5 to 16.3.
- The biggest single-benchmark swing is LMCA: 19% for o3-mini and 37.9% for Qwen3.5 397B-A17B.
- Qwen3.5 397B-A17B is cheaper at $0.60 / $3.60 per million input/output tokens, against $1.10 / $4.40 for o3-mini.
- Qwen3.5 397B-A17B accepts more context: 262K tokens versus 200K.
- Qwen3.5 397B-A17B has downloadable open weights; the other is API-only.
Side by side
| o3-mini | Qwen3.5 397B-A17B | |
|---|---|---|
| Provider | OpenAI | Alibaba (Qwen) |
| Noometry Index | 36.7 | 46.0 |
| Released | 2024-12-20 | 2026-02-01 |
| Weights | Proprietary | Open |
| Context window | 200K | 262K |
| Max output | 100K | 66K |
| Input $ / M tokens | $1.10 | $0.60 |
| Output $ / M tokens | $4.40 | $3.60 |
| Results tracked | 51 | 36 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen3.5 397B-A17B leads
o3-mini: 40.8 (#132), Qwen3.5 397B-A17B: 42.0 (#114)
| Benchmark | o3-mini | Qwen3.5 397B-A17B |
|---|---|---|
| LMArena Coding | 1378 | 1465 |
| Aider Polyglot | 60.4% | — |
| LMArena WebDev | — | 1400 |
| SciCode | 39.8% | — |
| GSO | 1.3% | — |
| WeirdML | 43.7% | — |
| LiveBench Coding | 82.7% | — |
| CadEval | 54% | — |
Agentic & Tool Use Qwen3.5 397B-A17B leads
o3-mini: 29.6 (#84), Qwen3.5 397B-A17B: 33.3 (#53)
| Benchmark | o3-mini | Qwen3.5 397B-A17B |
|---|---|---|
| APEX-Agents | — | 24.9% |
| τ²-bench Airline | — | 81.5% |
| τ²-bench Banking | — | 9.8% |
| τ²-bench Retail | — | 84.4% |
| τ²-bench Telecom | — | 97.8% |
| Cybench | 22.5% | — |
Reasoning Qwen3.5 397B-A17B leads
o3-mini: 16.3 (#305), Qwen3.5 397B-A17B: 34.5 (#70)
| Benchmark | o3-mini | Qwen3.5 397B-A17B |
|---|---|---|
| Chess Puzzles | 17% | 13% |
| LMArena Hard Prompts | 1366 | 1448 |
| Mystery Game Puzzles | 7% | 18% |
| DTBench | 68.8% | 87.5% |
| LMCA | 19% | 37.9% |
| Epoch Capabilities Index | 140.34 | 146.65 |
| ARC-AGI-2 | 3% | — |
| SimpleBench | 22.8% | — |
| Kagi LLM Benchmark | — | 73.7% |
| NYT Connections (extended) | — | 58.9% |
| ARC-AGI-1 | 34.5% | — |
| CritPt | 0.3% | — |
| Thematic Generalization | — | 65.1% |
| LiveBench Reasoning | 89.6% | — |
| LiveBench Data Analysis | 70.6% | — |
| ForecastBench | 59.6 | — |
| LiveBench | 75.9% | — |
Math Qwen3.5 397B-A17B leads
o3-mini: 28.1 (#244), Qwen3.5 397B-A17B: 46.1 (#73)
| Benchmark | o3-mini | Qwen3.5 397B-A17B |
|---|---|---|
| FrontierMath (Tiers 1-3) | 18.6% | 31.2% |
| OTIS Mock AIME 2024-2025 | 76.9% | 88.9% |
| LMArena Math | 1396 | 1454 |
| FrontierMath Tier 4 | 0% | — |
| LiveBench Math | 77.3% | — |
| MATH Level 5 | 96.5% | — |
| FrontierMath (Feb 2025 set) | 12.4% | — |
| FrontierMath Tier 4 (v1) | 4.2% | — |
Knowledge Qwen3.5 397B-A17B leads
o3-mini: 38.3 (#146), Qwen3.5 397B-A17B: 53.3 (#58)
| Benchmark | o3-mini | Qwen3.5 397B-A17B |
|---|---|---|
| GPQA Diamond | 77% | 86.4% |
| LMArena Expert | 1364 | 1462 |
| SimpleQA Verified | 15.3% | — |
| Confabulations | 17.9% | — |
Multimodal Not comparable
o3-mini: —, Qwen3.5 397B-A17B: 40.7 (#44)
| Benchmark | o3-mini | Qwen3.5 397B-A17B |
|---|---|---|
| LMArena Vision | — | 1263 |
Multilingual Qwen3.5 397B-A17B leads
o3-mini: 45.7 (#164), Qwen3.5 397B-A17B: 53.7 (#59)
| Benchmark | o3-mini | Qwen3.5 397B-A17B |
|---|---|---|
| LMArena Non-English | 1319 | 1430 |
| LMArena Chinese | 1379 | 1500 |
| LMArena French | 1334 | 1461 |
| LMArena German | 1303 | 1447 |
| LMArena Japanese | 1286 | 1426 |
| LMArena Korean | 1314 | 1384 |
| LMArena Russian | 1304 | 1429 |
| LMArena Spanish | 1321 | 1441 |
Instruction Following Too close to call
o3-mini: 75.1 (#72), Qwen3.5 397B-A17B: 75.0 (#77)
| Benchmark | o3-mini | Qwen3.5 397B-A17B |
|---|---|---|
| LMArena Instruction Following | 1337 | 1424 |
| LiveBench Instruction Following | 84.4% | — |
Long Context Qwen3.5 397B-A17B leads
o3-mini: 33.8 (#256), Qwen3.5 397B-A17B: 44.1 (#74)
| Benchmark | o3-mini | Qwen3.5 397B-A17B |
|---|---|---|
| LMArena Longer Query | 1343 | 1442 |
| Fiction.LiveBench | 50% | — |
Writing & Preference Qwen3.5 397B-A17B leads
o3-mini: 50.3 (#182), Qwen3.5 397B-A17B: 62.3 (#79)
| Benchmark | o3-mini | Qwen3.5 397B-A17B |
|---|---|---|
| LMArena Text | 1337 | 1438 |
| LMArena Creative Writing | 1286 | 1401 |
| LMArena Multi-Turn | 1320 | 1446 |
| Short-Story Creative Writing | 61.7% | — |
| EQ-Bench Creative Writing | — | 1478 |
| LiveBench Language | 50.7% | — |
Frequently asked questions
Is o3-mini better than Qwen3.5 397B-A17B?
Qwen3.5 397B-A17B is the stronger model overall, scoring 46.0 to 36.7 on the Noometry Index.
Which is cheaper, o3-mini or Qwen3.5 397B-A17B?
Qwen3.5 397B-A17B is cheaper. It lists at $0.60 per million input tokens and $3.60 per million output tokens; o3-mini lists at $1.10 and $4.40.
Is o3-mini or Qwen3.5 397B-A17B better for coding?
Qwen3.5 397B-A17B scores higher on coding benchmarks: 42.0 versus 40.8 in the Noometry coding category.
Which has the bigger context window?
Qwen3.5 397B-A17B does, with 262K tokens against 200K.
How many benchmarks do o3-mini and Qwen3.5 397B-A17B share?
25 benchmarks have published results for both models. o3-mini has 51 scored results on Noometry and Qwen3.5 397B-A17B has 36.